Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases where the rotational orientation of the coordinate system does not affect the meaning of the data (e.g. object classification). On the other hand, estimation/processing of rotations is necessary in cases where rotations are important (e.g. motion estimation). There has been recent progress in methods and theory in all these regards. Here we provide an overview of existing methods, both for 2D and 3D rotations (and translations), and identify commonalities and links between them.
Code (0)
등록된 구현이 없습니다.
Tasks
Motion EstimationSimilar Papers 제목 키워드 기반
R$^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
Vehicle detection is a significant and challenging task in aerial remote sensing applications. Most existing methods detect vehicles with regular rectangle boxes and fail to offer the orientation of vehicles. However, th…
Motion EstimationPositionRegion Proposalvehicle detectionRotatable and Movable Antenna-Enabled Near-Field Integrated Sensing and Communication
The aim of this article is to investigate the performance of near-field integrated sensing and communication (ISAC) systems using rotatable movable antennas (RMAs). In the proposed RMA-enabled system, the positions and r…
Integrated sensing and communicationISACA Demo of Radar Sensing Aided Rotatable Antenna for Wireless Communication System
Rotatable antenna (RA) represents a novel antenna architecture that enhances wireless communication system performance by independently or collectively adjusting each antenna's boresight/orientation. In this demonstratio…
Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-based Gaze Estimation
Appearance-based gaze estimation has been actively studied in recent years. However, its generalization performance for unseen head poses is still a significant limitation for existing methods. This work proposes a gener…
Domain GeneralizationGaze EstimationMultiplexed all-optical permutation operations using a reconfigurable diffractive optical network
Large-scale and high-dimensional permutation operations are important for various applications in e.g., telecommunications and encryption. Here, we demonstrate the use of all-optical diffractive computing to execute a se…
All